Skip to main content
Glama

booklint

by com.booklint
OverviewDiscussionsAdmin

Check an agent's actions against its owner's limits

check_book
Read-only

Deterministic rule checks of any agent's actions against the limits its owner wrote, the same as POST /v1/check. Send a trading book (snapshot and rulebook, optionally broker and journal) or an actions list with limits (per-transaction and daily spend caps, merchant allow and deny lists, refundability), or, BEFORE booking or subscribing, one offer with limits (Fine-Print Check: total price cap, mandatory fees over the headline price, refundability, free-cancellation window, auto-renewal, renewal price, trial length, and an optional page_text consistency scan; each rule answers MATCH, WARN, STOP or NOT_CHECKED with the figure found). Send plain text you already have. Do not send a URL; booklint will not fetch one. Returns verdict (FLAGGED, CLEAN, NOT_VERIFIED, REFUSED), coverage and flags. Each rule reports passed, failed or not checked; missing data is not checked, never assumed, and a result with zero flags is not a pass. Pass sample=true (sample 1, trading), sample="spend" (sample 2, purchasing and booking), sample="booking" (sample 3) or sample="subscription" (sample 4) with no key, never counted against the free caps, to see a full result. Without api_key the keyless free plan and its daily cap apply. Not advice; nothing is executed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_ofNoThe current UTC time (ISO 8601). Time rules use it; the server clock is never used.
offerNoOne offer, as structured fields your agent extracted: merchant, currency, headline_price, line_items [{label, amount, mandatory}], refund {refundable, free_cancel_until}, subscription {auto_renews, renewal_price, renewal_interval, trial_ends}. Send with limits.
brokerNoOptional broker export (desk checks).
limitsNoThe owner's limits: a rulebook (version, declared, rules).
sampleNotrue runs sample 1 (trading); "spend", "booking" or "subscription" runs sample 2, 3 or 4 instead.
actionsNoAn agent's actions: each {id, time (ISO 8601; days are UTC), amount, currency, merchant, refundable, kind}. Send with limits.
api_keyNoOptional key (vdk_...). Same as the Bearer header.
journalNoOptional journal of claims (desk checks).
rulebookNoThe agent's own rules.
snapshotNoThe book: positions, cash, as_of (ISO 8601).
page_textNoOptional plain text copied from the offer page, at most 64 KB. Scanned for amounts and refund or renewal phrases. Send plain text you already have. Do not send a URL; booklint will not fetch one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / as_of
      Added value: +{
+  "description": "The current UTC time (ISO 8601). Time rules use it; the server clock is never used.",
+  "type": "string"
+}
    • addedInput schema / properties / offer
      Added value: +{
+  "description": "One offer, as structured fields your agent extracted: merchant, currency, headline_price, line_items [{label, amount, mandatory}], refund {refundable, free_cancel_until}, subscription {auto_renews, renewal_price, renewal_interval, trial_ends}. Send with limits.",
+  "type": "object"
+}
    • addedInput schema / properties / page_text
      Added value: +{
+  "description": "Optional plain text copied from the offer page, at most 64 KB. Scanned for amounts and refund or renewal phrases. Send plain text you already have. Do not send a URL; booklint will not fetch one.",
+  "type": "string"
+}
    • changedInput schema / properties / sample / description
      Previous value: -"true runs sample 1 (trading); \"spend\" runs sample 2 instead."New value: +"true runs sample 1 (trading); \"spend\", \"booking\" or \"subscription\" runs sample 2, 3 or 4 instead."
    • changedInput schema / properties / sample / oneOf
      Previous value: -[
-  {
-    "type": "boolean"
-  },
-  {
-    "enum": [
-      "spend"
-    ],
-    "type": "string"
-  }
-]New value: +[
+  {
+    "type": "boolean"
+  },
+  {
+    "enum": [
+      "spend",
+      "booking",
+      "subscription"
+    ],
+    "type": "string"
+  }
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: the keyless free plan has a daily cap, missing data is 'not checked, never assumed', 'a result with zero flags is not a pass', the verdict vocabulary is disclosed, and it states nothing is executed and that it will not fetch URLs. This is exactly the kind of behavioral framing readOnlyHint alone cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and well organized around the three input modes, and nearly every sentence carries information. It is a dense wall of text with some overlap between the sample guidance and the description body, so it is not maximally tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, nested-object, no-output-schema tool, the description compensates by explaining the return shape (verdict, coverage, flags and per-rule passed/failed/not-checked statuses). An agent has enough to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3, but the description adds real semantics: what each input shape means, which offer fields are evaluated (mandatory fees over headline price, free-cancellation window, auto-renewal, renewal price, trial length), that page_text must be text you already have rather than a URL, and that as_of is used instead of the server clock.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('deterministic rule checks of any agent's actions against the limits its owner wrote') and ties itself to a known endpoint (POST /v1/check). It also enumerates the three distinct input modes (book, actions+limits, offer+limits), so an agent can tell exactly what this tool does without reading the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance per mode: send a book or an actions list for post-hoc checks, or 'BEFORE booking or subscribing' send one offer for the Fine-Print Check. It names the alternative path (pass sample=... to see a full result) and the fallback behavior without api_key, so selection reasoning is complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All booklint toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources